MPI-2 Benchmarks

MPI-2 Benchmarks#

Intel(R) MPI Benchmarks provides benchmarks for MPI-2 functions in two components: IMB-EXT and IMB-IO. The table below lists all MPI-2 benchmarks available and specifies whether they support the aggregate mode. For I/O benchmarks, the table also lists nonblocking flavors.

IMB-EXT#

Benchmark

Aggregate Mode

Non-blocking Mode

Window

Multi-Window

Unidir_Put

Multi-Unidir_Put

Supported

Unidir_Get

Multi-Unidir_Get

Supported

Bidir_Get

Multi-Bidir_Get

Supported

Bidir_Put

Multi-Bidir_Put

Supported

Accumulate

Multi-Accumulate

Supported

IMB-IO#

Benchmark

Aggregate Mode

Non-blocking Mode

Open_Close

Multi-Open_Close

S_Write_indv

Multi-S_Write_indv

Supported

S_IWrite_indv

Multi-S_IWrite_indv

S_Read_indv

Multi-S_Read_indv

S_IRead_indv

Multi-S_IRead_indv

S_Write_expl

Multi-S_Write_expl

Supported

S_IWrite_expl

Multi-IS_Write_expl

S_Read_expl

Multi-S_Read_expl

S_IRead_expl

Multi-IS_Read_expl

P_Write_indv

Multi-P_Write_indv

Supported

P_IWrite_indv

Multi-P_IWrite_indv

P_Read_indv

Multi-P_Read_indv

P_IRead_indv

Multi-P_IRead_indv

P_Write_expl

Multi-P_Write_expl

Supported

P_IWrite_expl

Multi-P_IWrite_expl

P_Read_expl

Multi-P_Read_expl

P_IRead_expl

Multi-P_IRead_expl

P_Write_shared

Multi-P_Write_shared

Supported

P_IWrite_shared

Multi-P_IWrite_shared

P_Read_shared

Multi-P_Read_shared

P_IRead_shared

Multi-P_IRead_shared

P_Write_priv

Multi-P_Write_priv

Supported

P_IWrite_priv

Multi-P_IWrite_priv

P_Read_priv

Multi-P_Read_priv

P_IRead_priv

Multi-P_IRead_priv

C_Write_indv

Multi-C_Write_indv

Supported

C_IWrite_indv

Multi-C_IWrite_indv

C_Read_indv

Multi-C_Read_indv

C_IRead_indv

Multi-C_IRead_indv

C_Write_expl

Multi-C_Write_expl

Supported

C_IWrite_expl

Multi-C_IWrite_expl

C_Read_expl

Multi-C_Read_expl

C_IRead_expl

Multi-C_IRead_expl

C_Write_shared

Multi-C_Write_shared

Supported

C_IWrite_shared

Multi-C_IWrite_shared

C_Read_shared

Multi-C_Read_shared

C_IRead_shared

Multi-C_IRead_shared

See Also